RichardErkhov/KnutJaegersberg_-_Deita-4b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Deita-4b - GGUF

• —Model creator: https://huggingface.co/KnutJaegersberg/
• —Original model: https://huggingface.co/KnutJaegersberg/Deita-4b/

Original model description: --- license: other datasets:

• —KnutJaegersberg/Deita-6k licensename: qwen licenselink: LICENSE model-index:
• —name: Deita-4b results:
• —task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2arc config: ARC-Challenge split: test args: numfew_shot: 25 metrics:
• —type: accnorm value: 46.08 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: numfewshot: 10 metrics:
• —type: accnorm value: 71.81 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: numfewshot: 5 metrics:
• —type: acc value: 55.46 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthfulqa config: multiplechoice split: validation args: numfewshot: 0 metrics:
• —type: mc2 value: 50.23 source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winograndexl split: validation args: numfew_shot: 5 metrics:
• —type: acc value: 66.14 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: numfewshot: 5 metrics:
• —type: acc value: 48.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=KnutJaegersberg/Deita-4b name: Open LLM Leaderboard ---

Prompt Example:

### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### User: 
How do you fine tune a large language model? 
### Assistant:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here